FFTS is a federated pretraining framework with a timescale-aware mixture-of-experts module that trains a time series foundation model from scratch across heterogeneous, non-shared datasets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Federated Foundation Models on Heterogeneous Time Series
FFTS is a federated pretraining framework with a timescale-aware mixture-of-experts module that trains a time series foundation model from scratch across heterogeneous, non-shared datasets.